© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 42820
    Prev
    Next
    INDEX
    Explanations

    installation and usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     then
    -1.79
     for
    -1.70
     when
    -1.68
    "
    -1.59
    -
    -1.58
     was
    -1.54
    </h1>
    -1.38
    </h4>
    -1.38
     de
    -1.33
    ]^{-
    -1.30
    POSITIVE LOGITS
    *///
    1.44
     compagnon
    1.38
    äldrar
    1.37
     herbes
    1.36
    rischen
    1.35
    Etimología
    1.35
     {;
    1.34
     susc
    1.34
     aborto
    1.32
     inaug
    1.31
    Activations Density 0.384%

    No Known Activations